Uses 992K of libraries. Click here for Pure Java version (1035L/7K).
!7 lib 1400180 // github.com/optimaize/language-detector lib 1400181 // jsonic lib 1011966 // slf4j-api-1.7.25.jar lib 1400182 // guava static LS _stickyLibs_langDetect = ll(#1400180, #1400181, #1011966, #1400182); import com.optimaize.langdetect.*; import com.optimaize.langdetect.i18n.*; import com.optimaize.langdetect.ngram.*; import com.optimaize.langdetect.profiles.*; import com.optimaize.langdetect.text.*; cmodule LanguageDetectorModule { transient LanguageDetector languageDetector; void init() { lock lock; if (languageDetector != null) ret; final new LanguageProfileReader profileReader; L<LanguageProfile> languageProfiles = map(ll("de", "en"), func(S lang) -> LanguageProfile { profileReader.readBuiltIn(LdLocale.fromString(lang)) }); languageDetector = LanguageDetectorBuilder.create(NgramExtractors.standard()) .withProfiles(languageProfiles) .build(); } // API // returns "en" or "de" or null S detectLanguage(S text) { S lang = dm_findAndCallModule("#1021121/WordToLanguageCRUD", 'languageForText, text); if (lang != null) ret languageToTwoLetters(lang); init(); L<DetectedLanguage> languages = languageDetector.getProbabilities(text); ret empty(languages) ? null : first(languages).getLocale().getLanguage(); } }
Began life as a copy of #1021122
download show line numbers debug dex old transpilations
Travelled to 7 computer(s): bhatertpkbcr, cfunsshuasjs, mqqgnosmbjvj, pyentgdyhuwx, pzhvpgtvlbxg, tvejysmllsmz, vouqrxazstgt
No comments. add comment
Snippet ID: | #1021123 |
Snippet name: | Language Detector (German/English) |
Eternal ID of this version: | #1021123/4 |
Text MD5: | 3540a0300976b4b3706e15f670d7a1a2 |
Transpilation MD5: | 5c185b5ae2f07a0933ff81f0969bb997 |
Author: | stefan |
Category: | javax / nlp |
Type: | JavaX source code (Dynamic Module) |
Public (visible to everyone): | Yes |
Archived (hidden from active list): | No |
Created/modified: | 2019-01-23 23:20:52 |
Source code size: | 1346 bytes / 39 lines |
Pitched / IR pitched: | No / No |
Views / Downloads: | 387 / 929 |
Version history: | 3 change(s) |
Referenced in: | #1021124 - dm_detectGermanVsEnglish - returns "en", "de" or null |